Qizhe Zhang

6

Papers

50

Total Citations

Papers (6)

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Gradient-based Parameter Selection for Efficient Fine-Tuning

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation